Background: With increased specialization of health care services and high levels of patient mobility, accessing health care services across multiple hospitals or clinics has become very common for diagnosis and treatment, particularly for patients with chronic diseases such as cancer. With informed knowledge of a patient’s history, physicians can make prompt clinical decisions for smarter, safer, and more efficient care. However, due to the privacy and high sensitivity of electronic health records (EHR), most EHR data sharing still happens through fax or mail due to the lack of systematic infrastructure support for secure, trustable health data sharing, which can also cause major delays in patient care. Objective: Our goal was to develop a system that will facilitate secure, trustable management, sharing, and aggregation of EHR data. Our patient-centric system allows patients to manage their own health records across multiple hospitals. The system will ensure patient privacy protection and guarantee security with respect to the requirements for health care data management, including the access control policy specified by the patient. Methods: We propose a permissioned blockchain-based system for EHR data sharing and integration. Each hospital will provide a blockchain node integrated with its own EHR system to form the blockchain network. A web-based interface will be used for patients and doctors to initiate EHR sharing transactions. We take a hybrid data management approach, where only management metadata will be stored on the chain. Actual EHR data, on the other hand, will be encrypted and stored off-chain in Health Insurance Portability and Accountability Act–compliant cloud-based storage. The system uses public key infrastructure–based asymmetric encryption and digital signatures to secure shared EHR data. Results: In collaboration with Stony Brook University Hospital, we developed ACTION-EHR, a system for patient-centric, blockchain-based EHR data sharing and management for patient care, in particular radiation treatment for cancer. The prototype was built on Hyperledger Fabric, an open-source, permissioned blockchain framework. Data sharing transactions were implemented using chaincode and exposed as representational state transfer application programming interfaces used for the web portal for patients and users. The HL7 Fast Healthcare Interoperability Resources standard was adopted to represent shared EHR data, making it easy to interface with hospital EHR systems and integrate a patient’s EHR data. We tested the system in a distributed environment at Stony Brook University using deidentified patient data. Conclusions: We studied and developed the critical technology components to enable patient-centric, blockchain-based EHR sharing to support cancer care. The prototype demonstrated the feasibility of our approach as well as some of the major challenges. The next step will be a pilot study with health care providers in both the United States and Switzerland. Our work provides an exemplar testbed to build next-generation EHR sharing infrastructures.

The suitability of peer-to-peer (P2P) approaches for full-text Web retrieval has recently been questioned because of the claimed unacceptable bandwidth consumption induced by retrieval from very large document collections. In this contribution we formalize a novel indexing/retrieval model that achieves high performance, cost-efficient retrieval by indexing with highly discriminative keys (HDKs) stored in a distributed global index maintained in a structured P2P network. HDKs correspond to carefully selected terms and term sets appearing in a small number of collection documents. We provide a theoretical analysis of the scalability of our retrieval model and report experimental results obtained with our HDK-based P2P retrieval engine. These results show that, despite increased indexing costs, the total traffic generated with the HDK approach is significantly smaller than the one obtained with distributed single-term indexing strategies. Furthermore, our experiments show that the retrieval performance obtained with a random set of real queries is comparable to the one of centralized, single-term solution using the best state-of-the-art BM25 relevance computation scheme. Finally, our scalability analysis demonstrates that the HDK approach can scale to large networks of peers indexing Web-size document collections, thus opening the way towards viable, truly-decentralized Web retrieval.

Advances in deep neural network (DNN) architectures have enabled new prediction techniques for stock market data. Unlike other multivariate time-series data, stock markets show two unique characteristics: (i) multi-order dynamics, as stock prices are affected by strong non-pairwise correlations (e.g., within the same industry); and (ii) internal dynamics, as each individual stock shows some particular behaviour. Recent DNN-based methods capture multi-order dynamics using hypergraphs, but rely on the Fourier basis in the convolution, which is both inefficient and ineffective. In addition, they largely ignore internal dynamics by adopting the same model for each stock, which implies a severe information loss. In this paper, we propose a framework for stock movement prediction to overcome the above issues. Specifically, the framework includes temporal generative filters that implement a memory-based mechanism onto an LSTM network in an attempt to learn individual patterns per stock. Moreover, we employ hypergraph attentions to capture the non-pairwise correlations. Here, using the wavelet basis instead of the Fourier basis, enables us to simplify the message passing and focus on the localized convolution. Experiments with US market data over six years show that our framework outperforms state-of-the-art methods in terms of profit and stability. Our source code and data are available at https://github.com/thanhtrunghuynh93/estimate.